com.webmcp-tool/agent-readiness

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Scores any public website on how usable it is by AI agents, with per-check evidence.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "agent-readiness": {
      "url": "https://webmcp-tool.com/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (5)

• score_site read-only

  Use this when the user asks whether a website is ready for AI agents, agent-ready, AI-agent friendly or WebMCP-ready, or what to fix so agents can use it. Scores one public website out of 100 for agent readiness and returns a grade, the fitness and adoption sub-scores, the five highest-value fixes, the scan time and whether the result came from cache. Reads one public page plus standard discovery files (robots.txt, /.well-known endpoints, sitemaps, llms.txt) and up to ten same-origin script bundles; it never logs in, submits forms or changes the site. Results are cached for about an hour.

  Parameters:

  • url (required) — string — Public http(s) address, for example example.com

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• explain_check read-only

  Use this when the user asks what a specific Agent Readiness finding means, why it matters to AI agents or how to fix it, usually after score_site. Explains one check: what it asks, why an agent cares, how it is weighted and how to fix it, with a code snippet where one exists. Answers from the rule set only and fetches nothing.

  Parameters:

  • checkId (required) — string — Check identifier, for example content-without-javascript

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_checks read-only

  Use this when the user asks what the Agent Readiness Score measures or how it is calculated, rather than how one site performs. Lists every check in the rule set with its pillar, weight and question. Fetches nothing.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_badge_embed read-only

  Use this when the user wants to show a site's Agent Readiness badge on that site. Scores the site if needed, then returns the HTML snippet for sites at grade C or better (bronze, silver or gold), or the reason and the first fixes when the site is not eligible. Returns HTML to paste; it installs nothing and runs no script.

  Parameters:

  • url (required) — string — Public http(s) address, for example example.com

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• watch_site

  Use this only when the user explicitly asks to be emailed when a site's Agent Readiness Score changes. Sends a confirmation email for monitoring that site. Use only when the user explicitly asks to receive a confirmation email for monitoring at the supplied address. Set sendConfirmationEmail to true only then. Monitoring starts only after the recipient opens the link and confirms on the page; this call itself sends one email.

  Parameters:

  • url (required) — string — Public http(s) address or bare host, for example example.com
  • email (required) — string — Address that will receive the confirmation and the alerts
  • sendConfirmationEmail (required) — boolean — True only after the user explicitly requests a monitoring confirmation email.

  Hints: read-only no · destructive no · idempotent no · open-world yes

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.